Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add emilvaintrub/ShowRunner --skill forgegit clone --depth 1 https://github.com/emilvaintrub/ShowRunnerWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/emilvaintrub/showrunner/forge)<a href="https://agentmods.dev/skills/emilvaintrub/showrunner/forge"><img src="https://agentmods.dev/badge/skills/emilvaintrub/showrunner/forge/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/emilvaintrub/showrunner/forge"><img src="https://agentmods.dev/badge/skills/emilvaintrub/showrunner/forge.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.00925 |
| Opus 5.5 | $0.00022 | $0.00370 |
| Sonnet 5.5 | $0.00011 | $0.00185 |
| Haiku 4.5 | $0.00006 | $0.00093 |
Grade A, and why
forge scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Forge
Turn intent into approved direction. Collaborate with the inventor; do not dispatch Forge runtime work.
Load
- Read
../core/lifecycle.mdand../core/method.md. - Read the active project's
.claude/showrunner/config.mdand the state ledger it names inlifecycle.state_file(default.claude/showrunner/state.md). - Read method.md.
- Load only the template required by the requested command.
Route
Forge runs project stages P2-P4 and initiative stages 2-6. The conductor
starts each one; the owner never has to name it. For discovery and
assessment, load discovery.md and
knowledge/inquiry-bank.md; for assessment,
also load ../core/evidence.md.
| Stage | Command | Output |
|---|---|---|
setup (Forge part) |
init |
Forge config section |
discovery |
discover |
owner profile; templates/discovery-brief.md after full inquiry coverage |
assessment |
assess |
templates/assessment.md with cited research and the owner's verdict |
constitution |
discover (constitution) |
templates/soul.md drawn from the confirmed brief and assessment, then automatic init re-validation |
roadmap |
plan |
initiative inquiry answers, then templates/project.md with ## Surfaces |
spec |
spec |
templates/spec.md sections 1-8 |
design |
design |
templates/designer-brief.md rendered through templates/adapters/<forge.designer_helper.tool>.md |
design-review |
design-review |
returned design output reviewed against the brief's Design Review Package |
handoff |
spec (sections 9-11) |
spec marked arc-ready |
steer is not a stage either: it runs whenever the owner raises an idea or
changes their mind, at any stage, following steering.md and
recording in templates/ideas-log.md. The conductor
starts it on its own when it classifies an owner message as an idea or steer.
What ships with it
16 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- agents/openai.yaml 194 B
- discovery.md 12 KB
- knowledge/inquiry-bank.md 9.9 KB
- method.md 19 KB
- steering.md 7.6 KB
- templates/adapters/figma-make.md 2.0 KB
- templates/adapters/v0.md 1.8 KB
- templates/assessment.md 3.7 KB
- templates/decision.md 625 B
- templates/designer-brief.md 8.1 KB
- templates/discovery-brief.md 1.7 KB
- templates/ideas-log.md 1.3 KB
- templates/project.md 840 B
- templates/questions.md 889 B
- templates/soul.md 1.1 KB
- templates/spec.md 3.5 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- today Changed · +1 lines 311d95ac5af4
- 1mo ago Changed · +23 lines 23e9ebb59267
- 2mo ago First seen · 50 lines · 55 tokens per session scan A 08f68d548bbf
forge is a skill published in the GitHub repository emilvaintrub/ShowRunner (2 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 925 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation. Continuation mode: infer requirements, state assumptions, propose design in one message — no Q&A loop.
ai-video-prompt-engineer
Use when the user wants to create AI video generation prompts for a brand, product, website, or topic. Includes interactive Q&A flow to gather requirements then outputs a single unified prompt (one paste) for tools like OmniFlash, Runway, Pika, Kling, Sora. Do NOT use for HyperFrames/Remotion video creation workflows.
frontend-security
Use this skill when writing or reviewing client-side code that renders user data, stores tokens, calls an API, or embeds third-party scripts - React/Next/Vue/Svelte or plain DOM. Covers XSS sinks, token storage, environment-variable leakage, CSP and security headers, iframe and postMessage trust, and the checks that…
api-contract-design
Use this skill when freezing the interface between a backend and its clients before parallel work starts, or when changing an endpoint other code already calls - request/response shapes, status codes, error envelope, pagination, filtering, idempotency, versioning, and the breaking-change rules. Covers writing the…
dependency-audit
Use this skill before adding a dependency, when an audit or Dependabot alert fires, or when a lockfile changes in a review - triaging CVEs by real reachability, spotting typosquats and install scripts, pinning and lockfile discipline, and license checks. Covers deciding what actually needs fixing instead of chasing…
graphyloop-waves
Use this skill when a request spans more than one layer (database + backend + frontend, or a feature plus a data pipeline). Turns the request into contract-first parallel waves with enforced dependencies, exclusive file ownership and per-lane acceptance checks, using the graphyloop planner and swarm.